- 
          
- 
                Notifications
    You must be signed in to change notification settings 
- Fork 10.9k
Closed
Labels
bugSomething isn't workingSomething isn't workinggood first issueGood for newcomersGood for newcomers
Description
Your current environment
The output of python collect_env.py
INFO 08-22 17:09:31 [__init__.py:241] Automatically detected platform cuda.
Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 24.04.1 LTS (x86_64)
GCC version                  : (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Clang version                : Could not collect
CMake version                : version 3.28.3
Libc version                 : glibc-2.39
==============================
       PyTorch Info
==============================
PyTorch version              : 2.7.1+cu126
Is debug build               : False
CUDA used to build PyTorch   : 12.6
ROCM used to build PyTorch   : N/A
==============================
      Python Environment
==============================
Python version               : 3.12.11 | packaged by Anaconda, Inc. | (main, Jun  5 2025, 13:09:17) [GCC 11.2.0] (64-bit runtime)
Python platform              : Linux-6.8.0-71-generic-x86_64-with-glibc2.39
==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : Could not collect
CUDA_MODULE_LOADING set to   : LAZY
GPU models and configuration : 
GPU 0: NVIDIA A800-SXM4-80GB
GPU 1: NVIDIA A800-SXM4-80GB
GPU 2: NVIDIA A800-SXM4-80GB
GPU 3: NVIDIA A800-SXM4-80GB
GPU 4: NVIDIA A800-SXM4-80GB
GPU 5: NVIDIA A800-SXM4-80GB
GPU 6: NVIDIA A800-SXM4-80GB
GPU 7: NVIDIA A800-SXM4-80GB
Nvidia driver version        : 550.163.01
cuDNN version                : Could not collect
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True
==============================
          CPU Info
==============================
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        46 bits physical, 57 bits virtual
Byte Order:                           Little Endian
CPU(s):                               64
On-line CPU(s) list:                  0-63
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) Gold 6346 CPU @ 3.10GHz
CPU family:                           6
Model:                                106
Thread(s) per core:                   2
Core(s) per socket:                   16
Socket(s):                            2
Stepping:                             6
CPU(s) scaling MHz:                   31%
CPU max MHz:                          3600.0000
CPU min MHz:                          800.0000
BogoMIPS:                             6200.00
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 intel_ppin ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
Virtualization:                       VT-x
L1d cache:                            1.5 MiB (32 instances)
L1i cache:                            1 MiB (32 instances)
L2 cache:                             40 MiB (32 instances)
L3 cache:                             72 MiB (2 instances)
NUMA node(s):                         4
NUMA node0 CPU(s):                    0-7,32-39
NUMA node1 CPU(s):                    8-15,40-47
NUMA node2 CPU(s):                    16-23,48-55
NUMA node3 CPU(s):                    24-31,56-63
Vulnerability Gather data sampling:   Mitigation; Microcode
Vulnerability Itlb multihit:          Not affected
Vulnerability L1tf:                   Not affected
Vulnerability Mds:                    Not affected
Vulnerability Meltdown:               Not affected
Vulnerability Mmio stale data:        Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Not affected
Vulnerability Spec rstack overflow:   Not affected
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected
==============================
Versions of relevant libraries
==============================
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.6.4.1
[pip3] nvidia-cuda-cupti-cu12==12.6.80
[pip3] nvidia-cuda-nvrtc-cu12==12.6.77
[pip3] nvidia-cuda-runtime-cu12==12.6.77
[pip3] nvidia-cudnn-cu12==9.5.1.17
[pip3] nvidia-cufft-cu12==11.3.0.4
[pip3] nvidia-cufile-cu12==1.11.1.6
[pip3] nvidia-curand-cu12==10.3.7.77
[pip3] nvidia-cusolver-cu12==11.7.1.2
[pip3] nvidia-cusparse-cu12==12.5.4.2
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-nccl-cu12==2.26.2
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] pyzmq==27.0.2
[pip3] torch==2.7.1
[pip3] torchaudio==2.7.1
[pip3] torchvision==0.22.1
[pip3] transformers==4.55.3
[pip3] transformers-v4.55.0-GLM-4.5V-preview==4.56.0.dev0
[pip3] triton==3.3.1
[conda] numpy                                    2.2.6                                        pypi_0           pypi
[conda] nvidia-cublas-cu12                       12.6.4.1                                     pypi_0           pypi
[conda] nvidia-cuda-cupti-cu12                   12.6.80                                      pypi_0           pypi
[conda] nvidia-cuda-nvrtc-cu12                   12.6.77                                      pypi_0           pypi
[conda] nvidia-cuda-runtime-cu12                 12.6.77                                      pypi_0           pypi
[conda] nvidia-cudnn-cu12                        9.5.1.17                                     pypi_0           pypi
[conda] nvidia-cufft-cu12                        11.3.0.4                                     pypi_0           pypi
[conda] nvidia-cufile-cu12                       1.11.1.6                                     pypi_0           pypi
[conda] nvidia-curand-cu12                       10.3.7.77                                    pypi_0           pypi
[conda] nvidia-cusolver-cu12                     11.7.1.2                                     pypi_0           pypi
[conda] nvidia-cusparse-cu12                     12.5.4.2                                     pypi_0           pypi
[conda] nvidia-cusparselt-cu12                   0.6.3                                        pypi_0           pypi
[conda] nvidia-nccl-cu12                         2.26.2                                       pypi_0           pypi
[conda] nvidia-nvjitlink-cu12                    12.6.85                                      pypi_0           pypi
[conda] nvidia-nvtx-cu12                         12.6.77                                      pypi_0           pypi
[conda] pyzmq                                    27.0.2                                       pypi_0           pypi
[conda] torch                                    2.7.1                                        pypi_0           pypi
[conda] torchaudio                               2.7.1                                        pypi_0           pypi
[conda] torchvision                              0.22.1                                       pypi_0           pypi
[conda] transformers                             4.55.3                                       pypi_0           pypi
[conda] transformers-v4-55-0-glm-4-5v-preview    4.56.0.dev0                                  pypi_0           pypi
[conda] triton                                   3.3.1                                        pypi_0           pypi
==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
Neuron SDK Version           : N/A
vLLM Version                 : 0.10.1rc2.dev145+g53415653f.d20250822 (git sha: 53415653f, date: 20250822)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      NV8     NV8     NV8     NV8     NV8     NV8     NV8     0-7,32-39       0               N/A
GPU1    NV8      X      NV8     NV8     NV8     NV8     NV8     NV8     0-7,32-39       0               N/A
GPU2    NV8     NV8      X      NV8     NV8     NV8     NV8     NV8     0-7,32-39       0               N/A
GPU3    NV8     NV8     NV8      X      NV8     NV8     NV8     NV8     0-7,32-39       0               N/A
GPU4    NV8     NV8     NV8     NV8      X      NV8     NV8     NV8     8-15,40-47      1               N/A
GPU5    NV8     NV8     NV8     NV8     NV8      X      NV8     NV8     8-15,40-47      1               N/A
GPU6    NV8     NV8     NV8     NV8     NV8     NV8      X      NV8     8-15,40-47      1               N/A
GPU7    NV8     NV8     NV8     NV8     NV8     NV8     NV8      X      8-15,40-47      1               N/A
Legend:
  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks
==============================
     Environment Variables
==============================
NCCL_CUMEM_ENABLE=0
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_cyrus
VLLM_WORKER_MULTIPROC_METHOD=spawn
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
I found that GLM-4.5V outputs repeat infinitely whenever n > 1. Notably, this occurs even when I only pass in text input and thinking is disabled.
Serve command:
vllm serve zai-org/GLM-4.5V -tp 4
Example:
from openai import OpenAI
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"
client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)
model = client.models.list().data[0].id
print("Model:", model)
normal_response = client.chat.completions.create(
    model=model,
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Who are you?"},
            ],
        }
    ],
    n=1,
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print("[Normal response]")
print(normal_response.choices[0].message.content)
buggy_response = client.chat.completions.create(
    model=model,
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Who are you?"},
            ],
        }
    ],
    n=2,  # n > 1
    max_tokens=8192,  # Otherwise this example would run for 20 mins until the context length is reached
    extra_body={"chat_template_kwargs": {"enable_thinking": False}},
)
print("[Buggy response]")
print(buggy_response.choices[0].message.content)
Notice in the buggy response, after the initial correct output, the model first incorrectly wraps the input with thinking tokens, and then enters an infinite loop where each repetition ends with </think>.
Output:
[Normal response]
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.
[Buggy response]
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.
<think>Who are you?</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate various types of information to help users solve problems and provide services.</think>
I am GLM-4.5V, an AI multimodal model developed by Z.AI, which can understand and generate
cc @njhill @ywang96 @zRzRzRzRzRzRzR
Before submitting a new issue...
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
Metadata
Metadata
Assignees
Labels
bugSomething isn't workingSomething isn't workinggood first issueGood for newcomersGood for newcomers